Instructions to use vllm-project/baichuan7b-zero-init with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use vllm-project/baichuan7b-zero-init with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("baichuan-inc/Baichuan-7B") model = PeftModel.from_pretrained(base_model, "vllm-project/baichuan7b-zero-init") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from vllm-project/baichuan7b-zero-init: direct link, hf CLI and curl.
- Browser
- Download file 555 Bytes
-
https://huggingface.co/vllm-project/baichuan7b-zero-init/resolve/main/README.md
- Command line
-
hf download hf://vllm-project/baichuan7b-zero-init/README.md
-
curl -L -o README.md https://huggingface.co/vllm-project/baichuan7b-zero-init/resolve/main/README.md
555 Bytes
metadata
library_name: peft
base_model: baichuan-inc/Baichuan-7B
This is a copy of jeeejeee/baichuan7b-zero-init at commit
9fd014b, made on 2026-10-30. vLLM CI uses this checkpoint and the original is on a personal account, so we keep a copy here to reduce supply-chain risk.
Model Card for Model ID
This LoRA model exclusively utilizes the unit tests from vLLM, and all the lora_B weights are initialized to zero.
Framework versions
- PEFT 0.10.0